Ramp Detection Research Articles

Keypoint-Based Bee Orientation Estimation and Ramp Detection at the Hive Entrance for Bee Behavior Identification System

This paper addresses the challenge of accurately estimating bee orientations on beehive landing boards, which is crucial for optimizing beekeeping practices and enhancing agricultural productivity. The research utilizes YOLOv8 pose models, trained on a dataset created using an open-source computer vision annotation tool. The annotation process involves associating bounding boxes with keypoints to represent bee orientations, with each bee annotated using two keypoints: one for the head and one for the stinger. The YOLOv8-pose models demonstrate high precision, achieving 98% accuracy for both bounding box and keypoint detection in 1024×576 px images. However, trade-offs between model size and processing speed are addressed, with the smaller nano model reaching 67 frames per second on 640×384 px images. The entrance ramp detection model achieves 91.7% intersection over union across four keypoints, making it effective for detecting the hive’s landing board. The paper concludes with plans for future research, including the behavioral analysis of bee colonies and model optimization for real-time applications.

Correlation analysis of wind power and meteorology based on the ramp detection method with adaptive sliding window

Abstract Since the penetration of wind power rises rapidly, the coupling between wind power and meteorology strengthens the dependence of the new power system on meteorology. The fluctuation of wind power and the ramp events become key challenges that affect the safe and stable operation of the power system. To balance the accuracy and efficiency of wind power ramp event detection, an adaptive sliding time window-based ramp event detection method is proposed, which includes three major steps: dataset preprocessing and compression, wind power ramp trend pattern extraction considering bump event screening, and wind power ramp detection based on adaptive sliding time window. The correlation between the ramp event of wind power and meteorological factors like temperature, wind speed and direction are analyzed, and the feasibility of the proposed method is verified. The results show that wind speed is the decisive meteorological factor influencing ramp events, and wind power is also affected by wind direction. However, the correlation between wind power and temperature is weak, which only works in a few ramp events.

Piecewise linear approximation for identifying wind power ramp events

WPREs (wind power ramp events) are one of the most critical factors affecting the security and protection of the electrical system. Accurate ramp event detection may help power systems better manage extreme events and reduce financial damage. In this study, We present an improved piecewise linear approximation for recognizing wind ramps in Kanyakumari district. In practise, wind power ramps can be decreased by properly managing and dispatching flexible reserve and associated services. This necessitates the use of proper ramp detection techniques as well as precise ramp forecasts. The method’s plan to break down wind power signal into increasing with increasing ramps, making ramp identification easier and ensuring that all conceivable ramps of varying lengths are identified. Using observed wind power data, the ramp detection method is used to assess the performance of an energy wind farm. The results reveal that identifying wind power ramps using the segmentation method is equivalent to optical ramp identification.

Analysing wind power ramp events and improving very short‐term wind power predictions by including wind speed observations

AbstractThough wind power predictions have been consistently improved in the last decade, persistent reasons for remaining uncertainties are sudden large changes in wind speed, so‐called ramps. Here, we analyse the occurrence of ramp events in a wind farm in Eastern Germany and the performance of a wind power prediction tool in forecasting these events for forecasting horizons of 15 and 30 min. Results on the seasonality of ramp events and their diurnal cycle are presented for multiple ramp definition thresholds. Ramps were found to be most frequent in March and April and least frequent in November and December. For the analysis, the wind power prediction tool is fed by different wind velocity forecast products, for example, numerical weather prediction (NWP) model and measurement data. It is shown that including observational wind speed data for very short‐term wind power forecasts improves the performance of the power prediction tool compared to the NWP reference, both in terms of ramp detection and in decreasing the mean absolute error between predicted and generated wind power. This improvement is enhanced during ramp events, highlighting the importance of wind observations for very short‐term wind power prediction.

A trend-based method for the prediction of offshore wind power ramp

Wind power ramp is a destructive event accompanied with a sharp change of wind power. Offshore wind power is expected to receive more attention for it can harvest consistent and strong winds. In this paper, a ramp detection framework based on the swinging door algorithm (SDA) and the mergence of correct ramps is proposed. Meanwhile, a trend-based prediction method (T-Method) is proposed to predict offshore wind power ramps. The ramp detection framework is utilized to identify wind power ramp events (WPREs) and label original data according to the detection results. After that, the labeled data is selected as the input of recurrent neural network to produce wind power prediction results. Finally, the prediction results are detected by the ramp detection framework to produce WPREs prediction results. Four recurrent neural network models and two traditional methods are applied to two offshore wind power datasets for corroborating the effectiveness of our method. Comparative experiments show that our proposed method performs excellent in all evaluation indicators. The proposed WPREs prediction method improves the performance of WPREs prediction under the premise of low false alarm rate and missing alarm rate. It provides early warning for power system operators to reduce the harm of WPREs.

Hybrid intrahour DNI forecast model based on DNI measurements and sky-imaging data

Short-term forecasting of direct normal irradiance (DNI), which refers to photons that did not interact with the atmosphere on their way to the observer, is of great interest in the advanced management of concentrated solar power systems. So, this paper exhibits a hybrid model dedicated to the intrahour forecasting of DNI (horizons are 5, 10, and 15 min). This hybrid model combines a knowledge-based model with a machine learning model: the knowledge-based model is used for clear-sky DNI forecasting from DNI measurements; the machine learning model evaluates the impact of the atmospheric disturbances on the solar resource, through the processing of high dynamic range sky images provided by a ground-based camera. The hybrid model is evaluated by comparing its performance, for different sky conditions, with that of two machine learning models based on past DNI observations only. The results highlight the pertinence of combining knowledge-based models with data-driven models, and of integrating sky-imaging data in the DNI forecasting process: the proposed hybrid model successfully manages clear-sky, overcast, and mixed situations. Regardless of the forecast horizon, the hybrid model outperforms the reference models both in normalized root mean squared error and in DNI ramp detection.

Study of the Algorithm for Wind Shear Detection with Lidar Based on Shear Intensity Factor

Low-level wind shear is a vital weather process affecting aircraft safety while taking off and landing and is known as the “aircraft killer” in the aviation industry. As a result, effective monitoring and warning are required. Several ramps detection algorithms for low-level wind shear based on glide path scanning of lidar have been developed, including double and simple ramp detection, with the ramp length extension and contraction strategies corresponding to the algorithm. However, current algorithms must be improved to determine the maximum shear value and location. In this paper, a new efficient algorithm based on the shear intensity factor value is presented, in which wind speed changes and distance are both considered when calculating wind shear. Simultaneously, the effectiveness of the improved algorithm has been validated through numerical simulation experiments. Results reveal that the improved algorithm can determine the maximum intensity value and wind shear location more accurately than the traditional algorithm. In addition, the new algorithm improved the detection ability of lidar for weak wind shear.

Wind power ramp event detection using a multi-parameter segmentation algorithm

The variable nature of wind power and the associated ramp events poses a number of operational challenges to grid operators, especially under high penetration of wind energy. These challenges typically relate to system stability, frequency control and dispatch. The adverse impacts of wind power ramps can be mitigated in practice through optimal scheduling and dispatch of flexible reserves and rapid response ancillary services. This, however, requires appropriate ramp detection algorithms, together with accurate ramp forecasting. This paper proposes a novel multi-parameter segmentation algorithm for the detection of wind power ramps. Ramp detection results are presented for a utility-scale wind farm, and the performance of the proposed algorithm is compared with existing algorithms, including the L1-ramp detect with sliding window and the optimized swinging door algorithm. The results show that the proposed algorithm is superior, particularly with reference to criteria such as ramp detection accuracy, computational expedience and ramp start- and end-point accuracy.

Algorithm for identifying wind power ramp events via novel improved dynamic swinging door

With the rapid increase in the penetration of wind power in recent years, wind power ramp events (WPREs) have become the main factors affecting the safety and stability of electric power systems. Accurate detection of ramp events could help power systems better manage the extreme events and reduce economic losses. The previous ramp detection methods are either too complex to implement that influence the computing efficiency, or based on the value of points which cannot completely reflect the trend of data segments and lead to a decrease of accuracy. Based on the above problems and the on-site requirements, this paper proposes a novel improved dynamic swinging door algorithm (ImDSDA) to optimise the state-of-the-art in WPREs detection. Firstly, the swinging door algorithm (SDA) is used to extract ramp segments. Secondly, the dynamic programming method is used for ramp trend identification and segment combination. Finally, raw data obtained from three real-world wind farms in Hubei, China were applied to validate the performance of the proposed ImDSDA. The detection results show that the ImDSDA is more accurate and efficient than the traditional detection methods and could be a feasible option for WPRE detection in power systems.

A simple methodology to detect and quantify wind power ramps

Abstract. Knowledge about the expected duration and intensity of wind power ramps is important when planning the integration of wind power production into an electricity network. The detection and classification of wind power ramps is not straightforward due to the large range of events that is observed and the stochastic nature of the wind. The development of an algorithm that can detect and classify wind power ramps is thus of some benefit to the wind energy community. In this study, we describe a relatively simple methodology using a wavelet transform to discriminate ramp events. We illustrate the utility of the methodology by studying distributions of ramp rates and their duration using 2 years of data from the Belgian offshore cluster. This brief study showed that there was a strong correlation between ramp rate and ramp duration, that a majority of ramp events were less than 15 h with a median duration of around 8 h, and that ramps with a duration of more than a day were rare. Also, we show how the methodology can be applied to a time series where installed capacity changes over time using Swedish onshore wind farm data. Finally, the performance of the methodology is compared with another ramp detection method and their sensitivities to parameter choice are contrasted.

Wind Power Ramp Event Forecasting Based on Feature Extraction and Deep Learning

In order to improve the accuracy of wind power ramp forecasting and reduce the threat of ramps to the safe operation of power systems, a wind power ramp event forecast model based on feature extraction and deep learning is proposed in this work. Firstly, the Optimized Swinging Door Algorithm (OpSDA) is introduced to detect wind power ramp events, and the extraction results of ramp features, such as the ramp rate, are obtained. Then, a ramp forecast model based on a deep learning network is established. The historical wind power and its ramp features are used as the input of the forecast model, thereby strengthening the model’s learning for ramp features and preventing ramp features from being submerged in the complex wind power signal. A Convolutional Neural Network (CNN) is adopted to extract features from model inputs to obtain the coupling relationship between wind power and ramp features, and Long Short-Term Memory (LSTM) is utilized to learn the time-series relationship of the data. The forecast wind power is used as the output of the model, based on which the ramp forecast result is obtained after the ramp detection. Finally, the wind power data from the Elia website is used to verify the forecast performance of the proposed method for wind power ramp events.

Low-Level Wind Shear Characteristics and Lidar-Based Alerting at Lanzhou Zhongchuan International Airport, China

Lanzhou Zhongchuan International Airport [International Civil Aviation Organization (ICAO) code ZLLL] is located in a wind shear prone area in China, where most low-level wind shear events occur in dry weather conditions. We analyzed temporal distribution and synoptic circulation background for 18 dry wind shear events reported by pilots at ZLLL by using the NCEP final (FNL) operational global analysis data, and then proposed a lidar-based regio-nal divergence algorithm (RDA) to determine wind shear intensity and location. Low-level wind shear at ZLLL usually occurs in the afternoon and evening in dry conditions. Most wind shear events occur in an unstable atmosphere over ZLLL, with changes in wind speed or direction generally found at 700 hPa and 10-m height. Based on synoptic circulations at 700 hPa, wind shear events could be classified as strong northerly, convergence, southerly, and weak wind types. The proposed RDA successfully identified low-level wind shear except one southerly case, achieving 94% alerting rate compared with 82% for the operational system at ZLLL and 88% for the ramp detection algorithm (widely used in some operational alert systems) based on the same dataset. The RDA-unidentified southerly case occurred in a near neutral atmosphere, and wind speed change could not be captured by the Doppler lidar.

Ramp events forecasting based on long‐term wind power prediction and correction

To mitigate the threat to power system caused by ramp events – large wind power fluctuation, this study proposes an advanced ramp prediction approach based on event detection framework. This approach contains two successive stages of work, including wind power forecasting and ramp detection. Considering high-performance ramp prediction requires long-term and accurate wind power prediction results; this study also proposes a hybrid prediction model at the first stage. By using wind power curve to reflect the physic mechanism of wind power generation, data from numerical weather prediction system could be used to realise long-term trend prediction. Then, a multivariate model is built with a data-mining algorithm to correct system errors of the primary prediction, which is addressed to improve long-term prediction performance. At the second stage, a modified swinging door algorithm is applied for ramp detection. Performance of both the proposed long-term wind power prediction and the corresponding ramp prediction are computed and compared with conventional models on an actual wind dataset. Comprehensive results validated the feasibility and superiority of the proposed ramp prediction approach.

Very short-term solar irradiance forecast using all-sky imaging and real-time irradiance measurements

A hybrid forecasting methodology to predict one-minute averaged solar irradiance one to ten minutes in advance is presented and evaluated. The methodology combines the use of all-sky images and irradiance measurements which are both processed in real time to produce the forecast. Pre-existing image processing techniques are locally adapted to estimate the mean motion of clouds, which is used to predict the future sun disk cover by clouds. Then, the predicted cloud information is converted into a solar irradiance estimate using the proposed model which uses real time measurements to extract its parameters for prediction. The validation of the method is done with a sample of 5238 forecasting time points, spread over a six-month period. The forecast uncertainty is assessed separately for clear, cloudy and partly cloudy days, revealing important characteristics of the model's performance under the different conditions. Under partly cloudy and highly variable conditions, positive forecasting skills with respect to regular persistence are achieved above forecasting horizons of two minutes, with a peak performance of 11.4% for forecasting horizons of six and ten minutes. The proposed model also outperforms a smart persistence model for all time horizons under these sky conditions. The model's ramp detection index (RDI, as defined in Chu et al. (2015)) is also evaluated for high and moderate ramps, achieving RDI indexes between 55 and 62% and between 43 and 49% for high and moderate ramps, respectively. These results show that in challenging highly variable solar irradiance conditions the proposed model is suitable for the very short term solar resource forecasting.

A parameter and resolution adaptive algorithm for rapid detection of ramp events in different timescale databases of the power system

The flexibility of the power system gets more attention of power system operators due to the high penetration of renewable energy sources. This leads to the need of the ramp detection. Based on the detection results of ramp events (REs) in historical and forecast databases, the assessment of flexibility requirements in the power system can be significantly improved. Thus the system operator is able to procure minimum ancillary services and design flexible ramping products. Furthermore, the accuracy of the ramp forecasting can be increased. In the mean time, the rapid development of measuring facilities in the power system, such as the WAMS and the SCADA system, requires a robust detecting method to detect ramp events in the databases with different data properties and resolutions of the power system. This paper proposes a Parameter and Resolution Adaptive Algorithm (PRAA) to identify REs fast and accurately. A fast search method that can process raw databases with tens of millions of data points in seconds is proposed to merge adjacent REs with the same ramp direction. The bad data processing method is directly integrated into the proposed algorithm. A post-processing method is developed to increase the accuracy and robustness of the proposed algorithm. The raw wind power data sets from Bonneville Power Authority (BPA) and a real-world power system in China are utilized to validate the performance of the proposed PRAA.

Cloud base height estimates from sky imagery and a network of pyranometers

Cloud base height (CBH) is an important parameter for physics-based high resolution solar radiation modeling. In sky imager-based forecasts, a ceilometer or stereographic setup is needed to derive the CBH; otherwise erroneous CBHs lead to incorrect physical cloud velocity and incorrect projection of cloud shadows, causing solar power forecast errors due to incorrect shadow positions and timing of shadowing events. In this paper, two methods to estimate cloud base height from a single sky imager and distributed ground solar irradiance measurements are proposed. The first method (Time Series Correlation, denoted as “TSC”) is based upon the correlation between ground-observed global horizontal irradiance (GHI) time series and a modeled GHI time series generated from a sequence of sky images geo-rectified to a candidate set of CBH. The estimated CBH is taken as the candidate that produces the highest correlation coefficient. The second method (Geometric Cloud Shadow Edge, denoted as “GCSE”) integrates a numerical ramp detection method for ground-observed GHI time series with solar and cloud geometry applied to cloud edges in a sky image. CBH are benchmarked against a collocated ceilometer and stereographically estimated CBH from two sky imagers for 15 min median-filtered CBHs. Over 30 days covering all seasons, the TSC method performs similarly to the GCSE method with nRMSD of 18.9% versus 20.8%. A key limitation of both proposed methods is the requirement of sufficient variation in GHI to enable reliable correlation and ramp detection. The advantage of the two proposed methods is that they can be applied when measurements from only a single sky imager and pyranometers are available.

An Uphill Safety Controller With Deep Learning-Based Ramp Detection for Intelligent Wheelchairs

In a society with aging population, the demand for electric wheelchairs is growing with the advancement of automation. However, many accidents have occurred due to the misjudgment of the slope angle and wheelchair speed while the wheelchair is traveling on ramps. This research employs the light electronic assistance pal compact motor package to reduce the weight and size of conventional electric wheelchairs. The modular design of proposed uphill controller and ramp detection functions allows users to easily select and incorporate only the functions they need. This paper proposes a ramp detection model implemented using the deep learning algorithm with CNN-4 structure to analyze depth image data. The model’s recognition time of each video frame is 11 times faster than that of the AlexNet and GoogleNet. The uphill safety controller is designed as an adaptive network-based fuzzy inference system with Q-learning. The safe speed is automatically calculated according to the angle obtained from slope classification and revised in real-time during the slope driving to prevent the user from moving towards the dangerous ramp or rolling back due to inadequate speed. The accuracy of ramp detection is further increased by 5% to 97.1% due to assistance from the voting system processing and the gyroscope output data. The 5° ramp experiment of our uphill controller with ramp classification takes 20 s to complete the slope driving which is 23% faster than the controller without ramp detection. The energy consumption is also one half less than the experiment without uphill detection.

Queue Length Estimation for Freeway Facilities: Based on Combination of Point Traffic Detector and Automatic Vehicle Identification Data

Queue length is a critical performance measure for assessing and managing transportation network performance. Two new methods that integrate data from point traffic detectors and automatic vehicle identification (AVI) readers to estimate the queue length of freeway segments for both off-line and real-time applications are developed in this study. One method estimates the queue length between two detectors by using linear interpolation between the travel time measurement based on AVI data when the link is fully queued and when no queue is present. In the second method, a segment with a partial queue is divided into two subsegments: the first is assumed to be similar to upstream traffic conditions and the second to downstream traffic conditions. Then, the length of each part is calculated from AVI speed data. The performance of these methods is assessed and compared in two case studies that are based on simulation data and real-world data. The results show that using a combination of point detector data and AVI data produces accurate estimates of queue length. The queue estimation method based on cumulative volumes collected with point detectors alone also produces reasonably good estimates but requires additional ramp detection and assumptions regarding moving queue density. The two combination methods produce results that are close to each other based on simulation data and real-world data. The segmentation method produces better results based on real-world data.

An edge model for the evaluation of wind power ramps characterization approaches

AbstractWind power forecasting is a recognized means of facilitating large‐scale wind power integration into power systems. Recently, there has been focus on developing dedicated short‐term forecasting approaches for large and sharp wind power variations, so‐called ramps. Accurate forecasts of specific ramp characteristics (e.g., timing and probability of occurrence) are important, as related forecast errors may lead to potentially large power imbalances, with a high impact on the power system. Various works about ramps’ periodicity or predictability have led to the development of new characterization approaches. However, a thorough analysis of these approaches has not yet been carried out. Such an analysis is necessary to ensure the reliability of subsequent conclusions on ramps’ characteristics. In this paper, we propose a comprehensive framework for evaluating and comparing different characterization approaches of wind power ramps. As a first step, we introduce a theoretical model of a ramp inspired from edge‐detection literature. The proposed model incorporates some important aspects of the wind power production process so as to reflect its non‐stationary and bounded aspects, as well as the random nature of ramp occurrences. Then, we introduce adequate evaluation criteria from signal‐processing and statistical literature, in order to assess the ability of an approach for reliably estimating ramp characteristics (i.e., timing and intensity). On the basis of simulations from this model and using the evaluation criteria, we study the performance of different ramp detection filters and multi‐scale characterization approaches. Our results show that some practical choices in wind‐energy literature are inappropriate, while others, namely, from signal‐processing literature, are preferable. Copyright © 2014 John Wiley & Sons, Ltd.

An Initial Study of Automatic Curb Ramp Detection with Crowdsourced Verification Using Google Street View Images

In our previous research, we examined whether minimally trained crowd workers could find, categorize, and assess sidewalk accessibility problems using Google Street View (GSV) images. This poster paper presents a first step towards combining automated methods (e.g., machine vision-based curb ramp detectors) in concert with human computation to improve the overall scalability of our approach.